Search papers, labs, and topics across Lattice.
This paper introduces StreamWSR, a streamable neural model for speech super-resolution that operates directly in the waveform domain. By utilizing a fully causal architecture and a compact frame-level representation, StreamWSR enables zero-look-ahead streaming inference without relying on vocoder-based reconstruction. Experimental results demonstrate that StreamWSR achieves competitive or superior speech quality and intelligibility compared to existing models, all while maintaining a lightweight design with only 9M parameters and 2G FLOPs.
StreamWSR achieves high-quality speech super-resolution with zero-look-ahead streaming, all in a compact model under 10 million parameters.
This paper proposes StreamWSR, a Streamable neural Waveform-domain model for speech Super-Resolution (SR). By adopting a fully causal architecture with compact frame-level waveform representation, the proposed StreamWSR supports zero-look-ahead streaming inference while avoiding vocoder-based reconstruction and explicit phase prediction. Specifically, StreamWSR downsamples the input waveform into a compact frame-level representation using strided causal convolutions. Then, a lightweight causal long-short-term modeling backbone is employed to capture both local waveform structures and long-range historical dependencies under causal constraints. Finally, the modeled output is converted back to the waveform domain through a causal transposed-convolution and combined with the input waveform via a residual connection to generate the final high-resolution speech. Experimental results on 16 kHz speech SR show that StreamWSR achieves competitive or superior speech quality and intelligibility compared with representative waveform- and spectrum-based baselines, while maintaining a zero-look-ahead streaming advantage with only 9M parameters and 2G FLOPs.
